Bringing-Old-Photos-Back-to-Life
Bringing-Old-Photos-Back-to-Life copied to clipboard
microsoft
Bringing Old Photo Back to Life (CVPR 2020 oral)
HI, I tried to generate mask for image of size 1180 * 768 It produced mask of size 1184 * 768 ``` D:\photo_restoration\Global>python detection.py --test_path input --output_dir output --input_size full_size...
Thanks for releasing the hr model. I have a question about the training details: I notice the hr model training script still get 256*256 images. The diff is using a...
Dear Wan， I'm a postgraduate student of Yunnan University in China. l just took my first step in scientific research focused on data mining and recommendation.Recently I read your paper...
Hi, could you please release the scratch detection training code? Thank you very much!
Hey! The code runs great on 1080ti and 1070ti produces quality processing. When I try to get the same result on 3090, but the code gives weird soapy images in...
Hi, After installation (which was quite tricky but somehow I finally did it), when running run.py (with --GPU -1 as i don't have nvidia card) I'm getting the following error:...
` Step 1/15 : FROM nvidia/cuda:11.1-base-ubuntu20.04 ---> 287475453634 Step 2/15 : RUN apt update && DEBIAN_FRONTEND=noninteractive apt install git bzip2 wget unzip python3-pip python3-dev cmake libgl1-mesa-dev python-is-python3 libgtk2.0-dev -yq --->...
I got this type of error message when implemented train_domain_A.py > File "train_domain_A.py", line 70, in losses, generated = model(Variable(data['label']), Variable(data['inst']), File "/home/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input,...
I think it will lose some info. Could please tell me why you set params like that. Thanks.
Could you share the code about how to synthesizing old photos ？I want to know more about the way to render realistic defects including the large-area photo damage and film...
